Very Long Instruction Word Processors (VLIW)

Very long instruction word (VLIW) ideas came from the parallel microcode way back in computing's earliest days and from the first supercomputers such as the Control Data CDC6600 and IBM 360/91. In the 1970s, many attached array processors and dedicated signal processors used VLIW-like wide instructions in ROM to compute fast Fourier transforms and other algorithms.


The first true VLIW machines were mini supercomputers in the early 1980s from three companies: Multiflow, Culler, and Cydrome. They were not a commercial success. Still, the compiler writing experience from these endeavors didn't go to waste, Hewlett Packard bought Multiflow, and now Josh Fisher (ex Mult iflow) and Bob Rau (ex Cy drome) lead HP's VLIW compiler effort. Trace scheduling and software pipelining, pioneered by Fisher and Rau, respectively, are now central pillars of VLIW compiler technology.
The trailblazing Multiflow 7/300 used two integer ALUs, two floating-point ALUs, and a branch unit (all built from multiple chips). Its 256-bit instruction word contained seven 32-bit operation codes. The integer units could each perform two operations per 130-ns cycle (four in all) for a performance of about 30 integer MIPS. You could also combine 7/300s to build 512 bit and 1024 bit wide machines.
Cydrome's pioneering Cydra 5 also used a 256-bit instruction word, with a special mode that executed each instruction as a sequence of six 40-bit operations. Its compilers could therefore generate a mix of parallel and conventional sequential code.
While both those VLIW machines used multiple chips, some regard Intel's i860 as the first single-chip VLIW. It depends on the compiler rather than on the hardware to sequence operations correctly.VLIW isn't solely for CPUs. Holland's Philips Semiconductors, another VLIW innovator, recently launched its VLIW TriMedia digital signal processor chip. TriMedia aims at high end applications such as multimedia PCs, videoconferencing, TV set-top boxes, and digital video cameras. The goal is to be fast enough to eliminate the need for a host CPU and cheap enough at $50 to keep total system cost down.


IBM Page for VLIW: http://www.research.ibm.com/vliw/tree_arch.html

Read More

_____________________________________________________________________

.Future of Computers      .DNA Computers      .Optical Computers 

.Holographic Storage Technology      .Quantum Computers

.Quantum Computing Reaches for True Power    

.Solid State Storage Technologies     .Protonic Memory   

.Molecular switches computers    .Nano-Computing

.Very Long Instruction Word Processors (VLIW)   

.Electronic Digital Paper     .Plastic Displays    

.Roentgen Display Technology    .Augmented reality

_____________________________________________________________________